Two Nvidia data center GPUs, one Blackwell Ultra and one Pascal: up to 288 GB HBM3e against 16 GB HBM2 and 11x the memory bandwidth on the B300.
At a glance
Updated 6 minutes ago- Memory
- 288 GB
- HBM3e
- Memory bandwidth
- 8.00 TB/s
- From
- $6.50 /GPU/hr
- 33 providers
- Memory
- 16 GB
- HBM2
- Memory bandwidth
- 732 GB/s
- From
- $1.27 /GPU/hr
- 5 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | B300 | P100 | Difference |
|---|---|---|---|
| On-demand | $6.50 | $1.27 | 5.1x more expensive on B300 |
| Spot | $4.30 | $0.77 | 5.6x more expensive on B300 |
| Reserved | $4.25 | $0.12 | 34x more expensive on B300 |
| Median | $7.89 | $1.53 | 5.1x more expensive on B300 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
B300 vs P100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B300 | P100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 16 GB HBM2 | 18x more on B300 |
| Bandwidth | 8,000 GB/s | 732 GB/s | 11x higher on B300 |
| Bus width | 8,192-bit | 4,096-bit | 2x wider on B300 |
| Compute · dense | |||
| FP4 | 14,000 TFLOPS | Not supported | B300 only |
| FP8 | 4,500 TFLOPS | Not supported | B300 only |
| FP16 / BF16 | 2,250 TFLOPS | 18.7 TFLOPS | 120x higher on B300 |
| INT8 | 153.5 TOPS | Not supported | B300 only |
| FP32 | 75 TFLOPS | 9.3 TFLOPS | 8.1x higher on B300 |
| FP64 | 1.2 TFLOPS | 4.7 TFLOPS | 3.9x higher on P100 |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | NVLink 160 GB/s | 11x higher on B300 |
| Board power | 1,100 W | 250 W | 4.4x higher on B300 |
| Released | Q1 2025 | Q2 2016 | 9 years newer on B300 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP16FP32FP64 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B300 datasheet and P100 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | B300 /GPU/hr | P100 /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $7.89 | -- |
Runpod
|
On-Demand $7.89 | -- |
Lium
|
On-Demand $8.00 | -- |
Vast.ai
|
On-Demand $12.13 | -- |
EmpirioLabs AI
|
On-Demand $16.00 | -- |
Spheron
|
Spot $5.85 | -- |
GPUaaS
|
Custom on request | -- |
Packet·ai
|
Custom on request | -- |
Scaleway
|
-- | On-Demand $1.42 |
Oracle Cloud
|
-- | On-Demand $1.27 |
Google Cloud
|
-- | On-Demand $1.51 |
Alibaba Cloud
|
-- | On-Demand $1.55 |
Database Mart
|
-- | Reserved (24mo) $0.12 |
33 providers list the B300 and 5 the P100. Every listing is on the B300 page and the P100 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia B300 was last updated on Sept. 7, 2026, and for Nvidia P100 on Sept. 7, 2026.